deepCover
DeblurGANv2
deepCover | DeblurGANv2 | |
---|---|---|
1 | 1 | |
4 | 976 | |
- | 2.8% | |
4.7 | 0.0 | |
9 months ago | almost 2 years ago | |
Shell | Python | |
- | GNU General Public License v3.0 or later |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
deepCover
DeblurGANv2
-
Implementing a CNN on an FPGA
I am trying to implement an image deblurring model (DeblurGANv2) The generator takes blurred images as an input and outputs the corrected image, the discriminator helps in training the generator. The model has been trained and I have run and deblurred images on a GPU. I am completely new to the domain of Machine learning and I am trying to implement this on an FPGA. I wanted your guys help on how to do this. The .h5 files contains the weights of the NN, how do I figure out its structure and put it on my FPGA. Can you please suggest some tools that might help or github links for people who have implemented similar stuff.
What are some alternatives?
uashield - Voluntary Ukraine security platform to protect us from Russian forces in the Internet
pix2pixHD - Synthesizing and manipulating 2048x1024 images with conditional GANs
StandWithUkraine - #StandWithUkraine banner and related documents
Pix2Vox - The official implementation of "Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images". (Xie et al., ICCV 2019)
ukraine-timemap - TimeMap instance for Civilian Harm in Ukraine
XVFI - [ICCV 2021, Oral 3%] Official repository of XVFI
pi-GAN-pytorch - Implementation of π-GAN, for 3d-aware image synthesis, in Pytorch
NAFNet - The state-of-the-art image restoration model without nonlinear activation functions.
Ghost-DeblurGAN - This is a lightweight GAN developed for real-time deblurring. The model has a super tiny size and a rapid inference time. The motivation is to boost marker detection in robotic applications, however, you may use it for other applications definitely.